From 7c3743fe5f2781a8aab9ba8e15f4d250963747cf Mon Sep 17 00:00:00 2001
From: Andrei Betlen <abetlen@gmail.com>
Date: Sun, 7 May 2023 00:12:47 -0400
Subject: [PATCH] Update llama.cpp

---
 llama_cpp/llama.py     | 4 ++++
 llama_cpp/llama_cpp.py | 8 ++++----
 vendor/llama.cpp       | 2 +-
 3 files changed, 9 insertions(+), 5 deletions(-)

diff --git a/llama_cpp/llama.py b/llama_cpp/llama.py
index fc91ea4..0db5c10 100644
--- a/llama_cpp/llama.py
+++ b/llama_cpp/llama.py
@@ -297,21 +297,25 @@ class Llama:
                 ctx=self.ctx,
                 candidates=llama_cpp.ctypes.pointer(candidates),
                 k=top_k,
+                min_keep=llama_cpp.c_size_t(1),
             )
             llama_cpp.llama_sample_tail_free(
                 ctx=self.ctx,
                 candidates=llama_cpp.ctypes.pointer(candidates),
                 z=llama_cpp.c_float(1.0),
+                min_keep=llama_cpp.c_size_t(1),
             )
             llama_cpp.llama_sample_typical(
                 ctx=self.ctx,
                 candidates=llama_cpp.ctypes.pointer(candidates),
                 p=llama_cpp.c_float(1.0),
+                min_keep=llama_cpp.c_size_t(1),
             )
             llama_cpp.llama_sample_top_p(
                 ctx=self.ctx,
                 candidates=llama_cpp.ctypes.pointer(candidates),
                 p=top_p,
+                min_keep=llama_cpp.c_size_t(1),
             )
             llama_cpp.llama_sample_temperature(
                 ctx=self.ctx,
diff --git a/llama_cpp/llama_cpp.py b/llama_cpp/llama_cpp.py
index ccec12c..527ed7c 100644
--- a/llama_cpp/llama_cpp.py
+++ b/llama_cpp/llama_cpp.py
@@ -515,7 +515,7 @@ def llama_sample_top_k(
     ctx: llama_context_p,
     candidates,  # type: _Pointer[llama_token_data_array]
     k: c_int,
-    min_keep: c_size_t = c_size_t(1),
+    min_keep: c_size_t,
 ):
     return _lib.llama_sample_top_k(ctx, candidates, k, min_keep)
 
@@ -534,7 +534,7 @@ def llama_sample_top_p(
     ctx: llama_context_p,
     candidates,  # type: _Pointer[llama_token_data_array]
     p: c_float,
-    min_keep: c_size_t = c_size_t(1),
+    min_keep: c_size_t,
 ):
     return _lib.llama_sample_top_p(ctx, candidates, p, min_keep)
 
@@ -553,7 +553,7 @@ def llama_sample_tail_free(
     ctx: llama_context_p,
     candidates,  # type: _Pointer[llama_token_data_array]
     z: c_float,
-    min_keep: c_size_t = c_size_t(1),
+    min_keep: c_size_t,
 ):
     return _lib.llama_sample_tail_free(ctx, candidates, z, min_keep)
 
@@ -572,7 +572,7 @@ def llama_sample_typical(
     ctx: llama_context_p,
     candidates,  # type: _Pointer[llama_token_data_array]
     p: c_float,
-    min_keep: c_size_t = c_size_t(1),
+    min_keep: c_size_t,
 ):
     return _lib.llama_sample_typical(ctx, candidates, p, min_keep)
 
diff --git a/vendor/llama.cpp b/vendor/llama.cpp
index 2edbdb0..1b0fd45 160000
--- a/vendor/llama.cpp
+++ b/vendor/llama.cpp
@@ -1 +1 @@
-Subproject commit 2edbdb0f99336cb41f0995061c7602ed54beb863
+Subproject commit 1b0fd454650ef4d68a980e3225488b79e6e9af25